Academic Journals Database
Disseminating quality controlled scientific knowledge

Multimodal Biometric Feature based Person Classification

ADD TO MY LIST
 
Author(s): Smita Thakre | Kalyani Mamulkar | Prachi Motghare | Pooja Godi | Ujwalla Gawande

Journal: International Journal of Computer Applications
ISSN 0975-8887

Volume: icwet;
Issue: 4;
Date: 2012;
Original page

Keywords: Multimodal Biometric | fingerprint recognition | Iris recognition | feature level fusion | SVM Classifier

ABSTRACT
A Monomodal Biometric system encounters a variety of security problems and presents sometimes unacceptable error rates. Conventional biometric system tends to have larger memory footprint, slower processing speed, and higher implementations and operational costs. Multiple biometric consist in combining two or more biometric modalities in a single identification system to improve the recognition accuracy. Whereas a state of art of framework for multimodal biometric identification system which can be adapted for any type of biometrics to provide smaller memory footprints and faster implementations than the conventional multimodal biometrics systems. In these paper we extract the feature of iris and fingerprint and fuse them at feature level and utilize SVM(Support Vector Machine) classifier for matching purpose to provide a higher accuracy than unimodal system.
Save time & money - Smart Internet Solutions      Why do you need a reservation system?